// SPDX-License-Identifier: GPL-2.0-only/* Copyright (c) 2016 Facebook */#include <linux/bpf.h>#include <linux/jhash.h>#include <linux/filter.h>#include <linux/kernel.h>#include <linux/stacktrace.h>#include <linux/perf_event.h>#include <linux/btf_ids.h>#include <linux/buildid.h>#include <linux/mmap_lock.h>#include "percpu_freelist.h"#include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK					\	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY |	\	 BPF_F_STACK_BUILD_ID) struct stack_map_bucket {	struct pcpu_freelist_node fnode;	u32 hash;	u32 nr;	u64 data[];}; struct bpf_stack_map {	struct bpf_map map;	void *elems;	struct pcpu_freelist freelist;	u32 n_buckets;	struct stack_map_bucket *buckets[] __counted_by(n_buckets);}; static inline bool stack_map_use_build_id(struct bpf_map *map){	return (map->map_flags & BPF_F_STACK_BUILD_ID);} static inline int stack_map_data_size(struct bpf_map *map){	return stack_map_use_build_id(map) ?		sizeof(struct bpf_stack_build_id) : sizeof(u64);} /** * stack_map_calculate_max_depth - Calculate maximum allowed stack trace depth * @size:  Size of the buffer/map value in bytes * @elem_size:  Size of each stack trace element * @flags:  BPF stack trace flags (BPF_F_USER_STACK, BPF_F_USER_BUILD_ID, ...) * * Return: Maximum number of stack trace entries that can be safely stored */static u32 stack_map_calculate_max_depth(u32 size, u32 elem_size, u64 flags){	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;	u32 max_depth;	u32 curr_sysctl_max_stack = READ_ONCE(sysctl_perf_event_max_stack); 	max_depth = size / elem_size;	max_depth += skip;	if (max_depth > curr_sysctl_max_stack)		return curr_sysctl_max_stack; 	return max_depth;} static int prealloc_elems_and_freelist(struct bpf_stack_map *smap){	u64 elem_size = sizeof(struct stack_map_bucket) +			(u64)smap->map.value_size;	int err; 	smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries,					 smap->map.numa_node);	if (!smap->elems)		return -ENOMEM; 	err = pcpu_freelist_init(&smap->freelist);	if (err)		goto free_elems; 	pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,			       smap->map.max_entries);	return 0; free_elems:	bpf_map_area_free(smap->elems);	return err;} /* Called from syscall */static struct bpf_map *stack_map_alloc(union bpf_attr *attr){	u32 value_size = attr->value_size;	struct bpf_stack_map *smap;	u64 cost, n_buckets;	int err; 	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)		return ERR_PTR(-EINVAL); 	/* check sanity of attributes */	if (attr->max_entries == 0 || attr->key_size != 4 ||	    value_size < 8 || value_size % 8)		return ERR_PTR(-EINVAL); 	BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64));	if (attr->map_flags & BPF_F_STACK_BUILD_ID) {		if (value_size % sizeof(struct bpf_stack_build_id) ||		    value_size / sizeof(struct bpf_stack_build_id)		    > sysctl_perf_event_max_stack)			return ERR_PTR(-EINVAL);	} else if (value_size / 8 > sysctl_perf_event_max_stack)		return ERR_PTR(-EINVAL); 	/* hash table size must be power of 2; roundup_pow_of_two() can overflow	 * into UB on 32-bit arches, so check that first	 */	if (attr->max_entries > 1UL << 31)		return ERR_PTR(-E2BIG); 	n_buckets = roundup_pow_of_two(attr->max_entries); 	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));	if (!smap)		return ERR_PTR(-ENOMEM); 	bpf_map_init_from_attr(&smap->map, attr);	smap->n_buckets = n_buckets; 	err = get_callchain_buffers(sysctl_perf_event_max_stack);	if (err)		goto free_smap; 	err = prealloc_elems_and_freelist(smap);	if (err)		goto put_buffers; 	return &smap->map; put_buffers:	put_callchain_buffers();free_smap:	bpf_map_area_free(smap);	return ERR_PTR(err);} static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault){	return may_fault ? build_id_parse(vma, build_id, NULL)			 : build_id_parse_nofault(vma, build_id, NULL);} static inline void stack_map_build_id_set_ip(struct bpf_stack_build_id *id){	id->status = BPF_STACK_BUILD_ID_IP;	memset(id->build_id, 0, BUILD_ID_SIZE_MAX);} static inline u64 stack_map_build_id_offset(unsigned long vm_pgoff,					    unsigned long vm_start, u64 ip){	return (vm_pgoff << PAGE_SHIFT) + ip - vm_start;} static inline void stack_map_build_id_set_valid(struct bpf_stack_build_id *id,						u64 offset,						const unsigned char *build_id){	id->status = BPF_STACK_BUILD_ID_VALID;	id->offset = offset;	if (id->build_id != build_id)		memcpy(id->build_id, build_id, BUILD_ID_SIZE_MAX);} /* * A cached VMA lookup result. The range [vm_start, vm_end) is always set. * vm_pgoff, file, build_id are set only when the build ID was resolved. * Zero vm_end marks the slot empty. build_id aliases the id_offs[] entry. */struct stack_map_cached_vma {	unsigned long vm_start;	unsigned long vm_end;	unsigned long vm_pgoff;	struct file *file; /* pinned in the sleepable path; NULL otherwise */	const unsigned char *build_id;}; /* * Per stack_map_get_build_id_offset() call cache of the last VMA with a build ID * resolved and the last VMA with no usable build ID. Adjacent stack frames tend * to land in the same VMA or the same backing file, so caching the last result * of each kind lets us skip unnecessary VMA lookups and build ID parse calls. * Keeping the two slots independent means a build-ID-less VMA doesn't evict the * last resolved build ID. */struct stack_map_build_id_cache {	struct stack_map_cached_vma resolved;	struct stack_map_cached_vma unresolved;}; /* * Fill @id from a cached range covering @ip. On a hit this writes @id (resolved * range -> build ID + offset, unresolved range -> raw ip) and returns 0; on a * miss it leaves @id untouched and returns -ENOENT. */static int stack_map_build_id_set_from_cache(struct stack_map_build_id_cache *cache,					     struct bpf_stack_build_id *id, u64 ip){	unsigned long vm_start, vm_end, vm_pgoff;	u64 offset; 	vm_start = cache->resolved.vm_start;	vm_end = cache->resolved.vm_end;	if (vm_end && ip >= vm_start && ip < vm_end) {		vm_pgoff = cache->resolved.vm_pgoff;		offset = stack_map_build_id_offset(vm_pgoff, vm_start, ip);		stack_map_build_id_set_valid(id, offset, cache->resolved.build_id);		return 0;	} 	vm_start = cache->unresolved.vm_start;	vm_end = cache->unresolved.vm_end;	if (vm_end && ip >= vm_start && ip < vm_end) {		stack_map_build_id_set_ip(id);		return 0;	} 	return -ENOENT;} /* * Record @vma's build ID as the last resolved one. @file is the pinned backing * file in the sleepable path (released when evicted), or NULL otherwise. */static void stack_map_build_id_cache_set_resolved(struct stack_map_build_id_cache *cache,						  struct file *file,						  const unsigned char *build_id,						  unsigned long vm_start,						  unsigned long vm_end,						  unsigned long vm_pgoff){	if (cache->resolved.file)		fput(cache->resolved.file);	cache->resolved = (struct stack_map_cached_vma){		.vm_start = vm_start,		.vm_end = vm_end,		.vm_pgoff = vm_pgoff,		.file = file,		.build_id = build_id,	};} /* Record [vm_start, vm_end) as a range with no usable build ID. */static void stack_map_build_id_cache_set_unresolved(struct stack_map_build_id_cache *cache,						    unsigned long vm_start,						    unsigned long vm_end){	cache->unresolved = (struct stack_map_cached_vma){		.vm_start = vm_start,		.vm_end = vm_end,	};} struct stack_map_vma_lock {	struct vm_area_struct *vma;	struct mm_struct *mm;}; /* * Acquire a stable read-side reference on the VMA covering @ip. * * With CONFIG_PER_VMA_LOCK=y this returns a VMA with its per-VMA read * lock held and mmap_lock dropped, so the caller may sleep. * * With CONFIG_PER_VMA_LOCK=n it returns a VMA with mmap_lock still * held; the caller must snapshot any fields it needs and pin vm_file * with get_file() before stack_map_unlock_vma() drops mmap_lock, as * the VMA may be split, merged, or freed after that. * * Returns NULL on failure, in which case no lock is held. */static struct vm_area_struct *stack_map_lock_vma(struct stack_map_vma_lock *lock, unsigned long ip){	struct mm_struct *mm = lock->mm;	struct vm_area_struct *vma; 	/* noop under !CONFIG_PER_VMA_LOCK */	vma = lock_vma_under_rcu(mm, ip);	if (vma) {		lock->vma = vma;		return vma;	} 	/*	 * Taking mmap_read_lock() is unsafe here, because the caller BPF	 * program might already hold it, causing a deadlock.	 */	if (!mmap_read_trylock(mm))		return NULL; 	vma = vma_lookup(mm, ip);	if (!vma) {		mmap_read_unlock(mm);		return NULL;	} #ifdef CONFIG_PER_VMA_LOCK	if (!vma_start_read_locked(vma)) {		mmap_read_unlock(mm);		return NULL;	}	mmap_read_unlock(mm);#endif 	lock->vma = vma;	return vma;} static void stack_map_unlock_vma(struct stack_map_vma_lock *lock){#ifdef CONFIG_PER_VMA_LOCK	vma_end_read(lock->vma);#else	mmap_read_unlock(lock->mm);#endif	lock->vma = NULL;} static void stack_map_get_build_id_offset_sleepable(struct bpf_stack_build_id *id_offs,						    u32 trace_nr){	struct stack_map_vma_lock lock = { .mm = current->mm };	struct stack_map_build_id_cache cache = {};	struct stack_map_cached_vma *res = &cache.resolved;	unsigned long vm_pgoff, vm_start, vm_end;	struct vm_area_struct *vma;	struct file *file;	u64 offset;	u64 ip; 	for (u32 i = 0; i < trace_nr; i++) {		ip = READ_ONCE(id_offs[i].ip); 		if (!stack_map_build_id_set_from_cache(&cache, &id_offs[i], ip))			continue; 		vma = stack_map_lock_vma(&lock, ip);		if (!vma) {			stack_map_build_id_set_ip(&id_offs[i]);			continue;		} 		vm_pgoff = vma->vm_pgoff;		vm_start = vma->vm_start;		vm_end = vma->vm_end; 		if (vma_is_anonymous(vma) || !vma->vm_file) {			stack_map_unlock_vma(&lock);			stack_map_build_id_set_ip(&id_offs[i]);			stack_map_build_id_cache_set_unresolved(&cache, vm_start, vm_end);			continue;		} 		file = vma->vm_file;		offset = stack_map_build_id_offset(vm_pgoff, vm_start, ip); 		/*		 * Same backing file as the last resolved VMA (another mapping		 * of the same ELF binary): reuse its build_id without re-parsing.		 */		if (file == res->file) {			stack_map_unlock_vma(&lock);			stack_map_build_id_set_valid(&id_offs[i], offset, res->build_id);			res->vm_start = vm_start;			res->vm_end = vm_end;			res->vm_pgoff = vm_pgoff;			continue;		} 		file = get_file(file);		stack_map_unlock_vma(&lock); 		/* build_id_parse_file() may block on filesystem reads */		if (build_id_parse_file(file, id_offs[i].build_id, NULL)) {			stack_map_build_id_set_ip(&id_offs[i]);			fput(file);			stack_map_build_id_cache_set_unresolved(&cache, vm_start, vm_end);			continue;		} 		stack_map_build_id_set_valid(&id_offs[i], offset, id_offs[i].build_id);		stack_map_build_id_cache_set_resolved(&cache, file, id_offs[i].build_id,						      vm_start, vm_end, vm_pgoff);	} 	if (res->file)		fput(res->file);} /* * Expects all id_offs[i].ip values to be set to correct initial IPs. * They will be subsequently: *   - either adjusted in place to a file offset, if build ID fetching *     succeeds; in this case id_offs[i].build_id is set to correct build ID, *     and id_offs[i].status is set to BPF_STACK_BUILD_ID_VALID; *   - or IP will be kept intact, if build ID fetching failed; in this case *     id_offs[i].build_id is zeroed out and id_offs[i].status is set to *     BPF_STACK_BUILD_ID_IP. */static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,					  u32 trace_nr, bool user, bool may_fault){	struct mmap_unlock_irq_work *work;	bool has_user_ctx = user && current && current->mm;	struct stack_map_build_id_cache cache = {};	struct vm_area_struct *vma;	int i; 	if (may_fault && has_user_ctx) {		stack_map_get_build_id_offset_sleepable(id_offs, trace_nr);		return;	} 	if (!has_user_ctx)		goto fallback; 	work = bpf_mmap_unlock_guard_get();	if (IS_ERR(work))		goto fallback; 	if (!mmap_read_trylock(current->mm)) {		bpf_mmap_unlock_guard_put(work);		goto fallback;	} 	for (i = 0; i < trace_nr; i++) {		u64 ip = READ_ONCE(id_offs[i].ip); 		if (!stack_map_build_id_set_from_cache(&cache, &id_offs[i], ip))			continue; 		vma = find_vma(current->mm, ip);		if (!vma || vma_is_anonymous(vma) ||		    fetch_build_id(vma, id_offs[i].build_id, may_fault)) {			/* per entry fall back to ips; cache build-ID-less range */			stack_map_build_id_set_ip(&id_offs[i]);			if (vma)				stack_map_build_id_cache_set_unresolved(&cache,						vma->vm_start, vma->vm_end);			continue;		}		/*		 * mmap_lock is held for the whole loop, so the cached VMA		 * fields stay valid; no file pinning is needed here.		 */		stack_map_build_id_set_valid(&id_offs[i],			stack_map_build_id_offset(vma->vm_pgoff, vma->vm_start, ip),			id_offs[i].build_id);		stack_map_build_id_cache_set_resolved(&cache, NULL, id_offs[i].build_id,						      vma->vm_start, vma->vm_end,						      vma->vm_pgoff);	}	bpf_mmap_unlock_mm(work, current->mm);	return; fallback:	/* cannot access current->mm, fall back to ips */	for (i = 0; i < trace_nr; i++)		stack_map_build_id_set_ip(&id_offs[i]);} static struct perf_callchain_entry *get_callchain_entry_for_task(struct task_struct *task, u32 max_depth){#ifdef CONFIG_STACKTRACE	struct perf_callchain_entry *entry;	int rctx; 	entry = get_callchain_entry(&rctx); 	if (!entry)		return NULL; 	entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip,					 max_depth, 0); 	/* stack_trace_save_tsk() works on unsigned long array, while	 * perf_callchain_entry uses u64 array. For 32-bit systems, it is	 * necessary to fix this mismatch.	 */	if (__BITS_PER_LONG != 64) {		unsigned long *from = (unsigned long *) entry->ip;		u64 *to = entry->ip;		int i; 		/* copy data from the end to avoid using extra buffer */

Lines 1–500 of 1155. Load more